Single-shot high dynamic range imaging via deep convolutional neural network

An, Vien Gia; Lee, Chul

doi:10.1109/apsipa.2017.8282319

Cited by 26 publications

(43 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we consider the SVE image with row-wise varying exposures in a single raw Bayer image using two different exposure times: a short exposure time ∆t S and a long exposure time ∆t L , as in [37]- [40]. We also consider the 2 × 2 RGGB color filter array, as shown in Figure 2.…”

Section: A Spatially Varying Exposure (Sve) Imagementioning

confidence: 99%

“…The L 2 loss was used in [40]. However, the L 2 loss penalizes larger errors and is tolerant of smaller errors, regardless of the underlying structures in an image [51].…”

Section: Loss Functionsmentioning

confidence: 99%

“…Recently, deep learning-based approaches to single-shot HDR imaging were developed [40], [41], which can reconstruct over-and under-exposed pixels in raw SVE Bayer images. While these algorithms synthesize high-quality HDR images, two persistent issues must be addressed.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, the demosaicing increases the computational complexity and may yield color artifacts. Second, both networks in [40], [41] are optimized with an L 2 loss, which is sensitive to large and small errors and does not correlate well to human perception [42]- [44]. Therefore, these algorithms often provide over-smoothed HDR images that are inconsistent with human visual perception, as we will discuss in Section IV.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Single-Shot High Dynamic Range Imaging via Multiscale Convolutional Neural Network

Vien

Lee

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

We propose a single-shot high dynamic range (HDR) imaging algorithm with row-wise varying exposures in a single raw image based on a deep convolutional neural network (CNN). We first convert a raw Bayer input image into a radiance map by calibrating rows with different exposures, and then we design a new CNN model to restore missing information at the under-and over-exposed pixels and reconstruct color information from the raw radiance map. The proposed CNN model consists of three branch networks to obtain multiscale feature maps for an image. To effectively estimate the high-quality HDR images, we develop a robust loss function that considers the human visual system (HVS) model, color perception model, and multiscale contrast. Experimental results on both synthetic and captured real images demonstrate that the proposed algorithm can achieve synthesis results of significantly higher quality than conventional algorithms in terms of structure, color, and visual artifacts.INDEX TERMS Spatially varying exposure (SVE) image, high dynamic range (HDR) imaging, convolutional neural network (CNN), and human visual system (HVS).

show abstract

Section: A Spatially Varying Exposure (Sve) Imagementioning

confidence: 99%

“…The L 2 loss was used in [40]. However, the L 2 loss penalizes larger errors and is tolerant of smaller errors, regardless of the underlying structures in an image [51].…”

Section: Loss Functionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Single-Shot High Dynamic Range Imaging via Multiscale Convolutional Neural Network

Vien

Lee

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…These make use of CNNs for a variety of problems related to HDR imaging, demonstrating various degrees of improvement over previous work. For example, there are CNNs for HDR reconstruction from multiple exposures in separate images [106,125,266] and from single-shot, spatially varying, exposures [9]. Other techniques attempt to estimate outdoor [115] and indoor [96] illumination maps from conventional LDR images.…”

Section: Deep Learning For Hdr Imagingmentioning

confidence: 99%